20 citations
- Centre National de la Recherche ScientifiqueFR4 papers
- CEA DAM Île-de-FranceFR2 papers
- Centre BorelliFR2 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR2 papers
- École Nationale Supérieure d’Informatique pour l’Industrie et l’EntrepriseFR2 papers
- Michelin (France)FR2 papers
- Sorbonne UniversitéFR2 papers
- Adventist Health Simi ValleyUS1 paper
- Biomécanique et BioingénierieFR1 paper
- Carthage CollegeUS1 paper
- CEA Paris-SaclayFR1 paper
- CEA Paris-Saclay - Etablissement de SaclayFR1 paper
11 papers
Learning features from Newton's algorithm: a way to accelerate nonlinear parametrized PDE solvers
Rémy Vallot, Florian de Vuyst, Thibault Dairay +1
It is well known that Newton's method converges faster when the initial guess is closer to a root of a system of nonlinear equations. In this paper, a two-stage Newton initial gues…
When Imbalance Comes Twice: Active Learning under Simulated Class Imbalance and Label Shift in Binary Semantic Segmentation
Julien Combes, Alexandre Derville, Jean-François Coeurjolly
The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expe…
PINCH: Pipeline-Informed Noise Characterization in LIGO's Third Observing Run
Zach Yarbrough, Andre Guimaraes, Prathamesh Joshi +2
We present a method to identify and categorize gravitational wave candidate triggers identified by matched filtering gravitational wave searches (pipelines) caused by transient noi…
Giant mobility of surface-trapped ionic charges following liquid tribocharging
Zouhir Benrahla, Tristan Saide, Louis Burnaz +3
The sliding motion of aqueous droplets on hydrohobic surfaces leads to charge separation at the trailing edge, with implications from triple-line friction to hydrovoltaic energy ge…
Geometry-aware framework for deep energy method: an application to structural mechanics with hyperelastic materials
Thi Nguyen Khoa Nguyen, Thibault Dairay, Raphaël Meunier +2
Physics-Informed Neural Networks (PINNs) have gained considerable interest in diverse engineering domains thanks to their capacity to integrate physical laws into deep learning mod…
Toward industrial use of continual learning : new metrics proposal for class incremental learning
Konaté Mohamed Abbas, Anne-Françoise Yao, Thierry Chateau +1
In this paper, we investigate continual learning performance metrics used in class incremental learning strategies for continual learning (CL) using some high performing methods. W…